© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 16056
    Prev
    Next
    INDEX
    Explanations

    words in historical political texts, especially related to power/money changing hands.

    oai_token-act-pair · gemini-2.0-flash

    Historical monetary contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Géographie
    -0.48
    GHIJKLM
    -0.47
    DebuggerNonUser
    -0.44
     manifestación
    -0.41
    ViewImports
    -0.41
    нном
    -0.40
    stagland
    -0.40
     veto
    -0.40
    SocketChannel
    -0.40
    rotor
    -0.39
    POSITIVE LOGITS
    TintMode
    0.81
    WebVitals
    0.75
     ExecuteAsync
    0.75
    PreferredItem
    0.75
     الرياضيه
    0.72
    RTEE
    0.71
     disponibilités
    0.71
    yntaxException
    0.70
    曖昧さ回避
    0.68
     Préférences
    0.68
    Activations Density 3.657%

    No Known Activations